ingest

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare this is a non-read-only, non-idempotent, non-destructive mutation; the description adds the async daemon behavior and the per-CLI bounding of max_msgs, which the annotations do not cover. However, it never addresses the idempotency risk (repeated manual calls potentially re-ingesting or duplicating) or any cost/rate implications, which is the most important behavioral fact for a non-idempotent write.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences with no filler, and the async-default-before-manual ordering is front-loaded correctly. Slightly dense but every sentence carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be explained, complexity is low (one optional integer param), and the description covers timing, trigger conditions, and parameter meaning. The remaining gap is the non-idempotent call semantics, which an agent should know before invoking manually.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and there is one parameter, so the description must carry the meaning: 'bounds the new messages taken from each CLI' meaningfully explains both direction and scope (per-CLI, not global). It does not explain the default of 5000 or what happens when the bound truncates.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Ingest new transcripts'), which is clear despite the tool name 'ingest' being generic on its own. No sibling tool competes for the same job, so differentiation pressure is low, but the description never says what a 'transcript' is or where they come from.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states the default path (initial and periodic passes run asynchronously in the daemon host) and the manual trigger conditions (backfill, or after a long absence). That is real when-to-use guidance, though it doesn't say what happens if you call it while the daemon is already ingesting.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.